© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15247
    Prev
    Next
    INDEX
    Explanations

    financial items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å²Ĺ
    -0.20
    æĬļ
    -0.18
    åĴĮå¹³
    -0.18
    ç»°
    -0.18
    訴
    -0.17
    åľ¨éĩĮéĿ¢
    -0.17
    鼷æĸ¯
    -0.17
    Intensity
    -0.17
    Extent
    -0.17
    orado
    -0.17
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.28
    èµĦäº§è´ŁåĢº
    0.21
    ä¸Ĭæľī
    0.21
     items
    0.20
    åı¦ä¸Ģè¾¹
    0.19
    _=
    0.19
    平衡
    0.19
    æł¸ç®Ĺ
    0.19
    èijŃ
    0.18
     Items
    0.18
    Activations Density 0.015%

    No Known Activations